---
library_name: granite_tsfm
base_model: ibm-granite/granite-timeseries-ttm-r2
tags:
- ttm4hvac
- tsfm
- digital twin
- hvac
- energy
- experiment
license: apache-2.0
datasets:
- gft/ttm4hvac-target-default-train
- gft/ttm4hvac-target-heat-test
- gft/ttm4hvac-target-cool-test
pipeline_tag: time-series-forecasting
papers:
- title: "Transfer learning of building dynamics digital twin for HVAC control with Time-series Foundation Model"
  url: https://arxiv.org/abs/XXXX.XXXXX
  authors: "Ferran Aran Domingo"
---

# TTM4HVAC – TinyTimeMixer for HVAC dynamics modeling 

This repository contains the **TTM4HVAC – target-default** fine-tuned TinyTimeMixer model.

It corresponds to the **“target-default” experiment** from the TTM4HVAC paper, where the model is fine-tuned solely on **default RBC data from the target building** (BestestAir, Denver climate).

This checkpoint is part of the TTM4HVAC experiment family.  
For the main model, recommended usage, detailed examples, and full documentation, please see:

👉 **Main model card:** https://huggingface.co/gft/ttm4hvac